SillyTavern 1.12.5

Breaking changes

This release includes several breaking changes to STscript. Please follow the STscript section below to update your scripts.

Backends

• OpenAI: added chatgpt-4o-latest to the list of models.
• Block Entropy: added as a Chat Completion source.
• TogetherAI: now supports min_p, presence_penalty and frequency_penalty sampling parameters.
• Ollama: now supports min_p sampling parameter. keep_alive setting can be configured in config.yaml.
• Claude: added a config.yaml option to enable experimental system prompt caching.
• Perplexity: added Llama 3.1 models to the list.
• Google MakerSuite: renamed to Google AI Studio.
• Featherless: model list now shows the maximum context size and automatically sets the context size for the selected model.
• Added a tokenizer for Gemma and Gemini models.

Improvements

• Macros in first messages are now synchronized between the display and the prompt.
• Server: the host protocol can now be configured in config.yaml. Choose between IPv4 (default), IPv6, or both.
• World Info: disabling an entry is now possible without changing its constant status.
• World Info: added an option to limit max recursion depth. Conflicts with min activations.
• Text Completion: Mirostat settings block is now not displayed on sources where it is not supported.
• Text Completion: names as stopping strings can now be toggled in Advanced Formatting under Context Settings.
• Chat Completion: group nudge won't be inserted when impersonating in groups.
• Tags: backup imports can now either overwrite or skip existing tags.
• Tags: added import options to bulk tag editing menu.
• Added a configuration option to auto-select the input field contents in popups.
• Added a configuration option to enable quick impersonation button.
• Model cache for transformers.js has been moved under the data root directory.

Extensions

• Image Captioning: raised or removed (if applicable) a token limit for multimodal captioning.

• Character Gallery: images are now sorted by ascending date.

• TTS: added an "OpenAI-compatible" endpoint source.

• Summarization: added an experimental WebLLM extension summarization source.

• Character Expressions: "LLM" classification source now uses raw prompt generation method.

• Image Generation:

  • Added Block Entropy and Hugging Face Inference API as image generation sources.
  • Added image swipes for image rerolls and cycling through generated images.
  • Added a separate stop button to cancel image generation (located in the wand menu).

• Quick Reply:

  • QR panel popup button can now be hidden.
  • Quick Reply buttons can now use an icon instead of, or in addition to, their label text.
  • Quick Reply Sets can now be assigned colors to highlight the buttons.
  • Added a basic debugger to the Quick Reply editor.
  • Added UI shortcuts for copying or moving quick replies between sets.
  • Added an option to auto-execute QR on new chat creation.

STscript

The piped value from a parent closure will no longer be automatically injected into the first command of a child closure. You can still explicitly reference the parent's piped value with {{pipe}}, but if you leave the unnamed argument of the first command inside a closure blank, the value will not be automatically injected.

Messages added by Image Generation and Image Captioning extensions now emit events that can trigger QR auto-execution.

• Added support for block comments.
• /run command: can now execute closures directly, in addition to QRs and closure variables.
• /break command: added to break out of a loop (/while or /times) or a closure early.
• /addswipe command: added switch parameter to display a new swipe immediately.
• /api-url command: added to get/set server URL for compatible APIs.
• /tokenizer command: added to choose a preferred tokenizer.
• /gen command: now supports empty prompts.
• /api and /summarize now support quiet parameter to hide toast notifications.

STscript documentation: https://docs.sillytavern.app/usage/st-script/

Bug fixes

• Fixed Google Translate API response decoding. No more ��.
• Fixed being unable to toggle DRY sampling block with sampler select.
• Fixed rendering of underscore italics Markdown in code blocks.
• Fixed expanded custom CSS editor not applying changes to the styles.
• Fixed OpenRouter providers selection not being loaded on app start.
• Fixed sluggish performance of WI editor when editing large books.
• Fixed lazy loading of chat when all visible messages were deleted.
• Fixed using legacy API paths for sources where it was not supported.
• Fixed automatic TTS narration of messages hidden from prompts.
• Fixed a placeholder TTS text causing ghost narration on mobile.
• Fixed vector storage applying summarization to files and WI entries.
• Fixed entity name prefix trimming even if name display is preferred.
• Fixed macros not being replaced in DRY penalty sequence breakers.

Community updates

• Update zh-cn.json by @steve02081504 in https://github.com/SillyTavern/SillyTavern/pull/2573
• Fix: Properly handle text responses when character name is not provided in sendas cmd by @joenunezb in https://github.com/SillyTavern/SillyTavern/pull/2577
• /theme allows returning current theme & fix /theme and /bg doc by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2572
• Improve building CONNECT_API_MAP by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2578
• Fix colors resetting on Tag Management dragging by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2579
• Staging by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/2580
• fix typo by @Kas1o in https://github.com/SillyTavern/SillyTavern/pull/2589
• Add eventSource for generate_data, export functions for streaming/generation request by @splitclover in https://github.com/SillyTavern/SillyTavern/pull/2590
• Update 'zh-cn' translation by @steve02081504 in https://github.com/SillyTavern/SillyTavern/pull/2583
• Fix "show more messages" on empty chat by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2587
• Improve Tag Backup Restore functionality by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2582
• Parser followup 2 by @LenAnderson in https://github.com/SillyTavern/SillyTavern/pull/2415
• Update MakerSuite temperature caps by @Succubyss in https://github.com/SillyTavern/SillyTavern/pull/2592
• Gemini-related updates; adds gemini-1.5-pro-exp-0801 by @Succubyss in https://github.com/SillyTavern/SillyTavern/pull/2600
• Gemini max context size corrections, option selector update by @Succubyss in https://github.com/SillyTavern/SillyTavern/pull/2602
• Update zh-cn.json by @steve02081504 in https://github.com/SillyTavern/SillyTavern/pull/2608
• WI blackbox begone (Export, document and refactor a bit of the WI API) by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2601
• Image generation stop handling by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/2594
• Fix incorrect JanitorAI/JannyAI import due to incorrect HTTP header by @ayancey in https://github.com/SillyTavern/SillyTavern/pull/2611
• Added quick Regenerate and Impersonate buttons by @NearEDGE in https://github.com/SillyTavern/SillyTavern/pull/2598
• fix: LLM Classifier Defaulting to Last Spoken Character's Expression For All Characters in Group Chats by @Bronya-Rand in https://github.com/SillyTavern/SillyTavern/pull/2605
• Major WI performance improvements on UI usage by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2615
• Update zh-cn.json by @steve02081504 in https://github.com/SillyTavern/SillyTavern/pull/2618
• Add GPT-4o checkpoint model (support Structured Output) by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2623
• Improve /addswipe and /delswipe slightly by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2629
• Add events for chat completion import/export by @splitclover in https://github.com/SillyTavern/SillyTavern/pull/2634
• Group members as stopping strings only added if generating for a specific member or impersonating by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2636
• Split WI Entry 'disable' into separate toggle by @RossAscends in https://github.com/SillyTavern/SillyTavern/pull/2635
• Adding Block Entropy API endpoints for chat, image, and video generation by @edk208 in https://github.com/SillyTavern/SillyTavern/pull/2640
• OpenAI Compatible API TTS Provider by @ayancey in https://github.com/SillyTavern/SillyTavern/pull/2654
• Summarize with WebLLM extension by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/2651
• Quick Replies: Add auto-execute on new chat by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/2656
• Bump axios from 1.6.1 to 1.7.4 by @dependabot in https://github.com/SillyTavern/SillyTavern/pull/2659
• Bump axios from 1.7.2 to 1.7.4 in /tests by @dependabot in https://github.com/SillyTavern/SillyTavern/pull/2660
• Image Generation: Add swipes for generated images by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/2655
• support for Ipv6 by @BPplays in https://github.com/SillyTavern/SillyTavern/pull/2593
• Move transformers.js model cache under the data root by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/2667
• Don't trim names in message prefixes if allowed with settings by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/2669
• enable vision for chatgpt-4o-latest by @cuteanon in https://github.com/SillyTavern/SillyTavern/pull/2673
• Add bulk tag import by @d-ber in https://github.com/SillyTavern/SillyTavern/pull/2663
• /api-url slash command to get/set the API server url for text gen and OpenAI Custom by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2675
• Open popups should block all default hotkeys by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2677
• Enable auto-select of input field on popups + Add "auto-select" utility class by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2550
• /messages callback refactored to async by @Succubyss in https://github.com/SillyTavern/SillyTavern/pull/2682
• Don't replace underscore italics inside of code blocks by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/2679
• Add slash command to set tokenizer by @eugencowie in https://github.com/SillyTavern/SillyTavern/pull/2683
• Tag import fixed, again. (accepts char avatar key) by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2685
• Wait for settings before reloading after toggling extensions by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/2686
• Improve WI Character Filter description by @Wolfsblvt in https://github.com/SillyTavern/SillyTavern/pull/2687
• Hugging Face Inference API Image Generation by @ayancey in https://github.com/SillyTavern/SillyTavern/pull/2688
• Suspend macros in first messages by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/2674
• Add quiet flags to /api and /summarize by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/2691
• QR: Add toggle to hide popout button by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/2692
• Implements max recursion depth for lorebooks by @honey-tree in https://github.com/SillyTavern/SillyTavern/pull/2698
• Cull the usage of MAG in streaming by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/2700
• Staging by @Cohee1207 in https://github.com/SillyTavern/SillyTavern/pull/2705

New Contributors

• @Kas1o made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/2589
• @ayancey made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/2611
• @NearEDGE made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/2598
• @edk208 made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/2640
• @dependabot made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/2659
• @BPplays made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/2593
• @cuteanon made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/2673
• @d-ber made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/2663
• @eugencowie made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/2683
• @honey-tree made their first contribution in https://github.com/SillyTavern/SillyTavern/pull/2698

Full Changelog: https://github.com/SillyTavern/SillyTavern/compare/1.12.4...1.12.5